x86, fpu: Avoid FPU lazy restore after suspend

When a cpu enters S3 state, the FPU state is lost.
After resuming for S3, if we try to lazy restore the FPU for a process running
on the same CPU, this will result in a corrupted FPU context.

Ensure that "fpu_owner_task" is properly invalided when (re-)initializing a CPU,
so nobody will try to lazy restore a state which doesn't exist in the hardware.

Tested with a 64-bit kernel on a 4-core Ivybridge CPU with eagerfpu=off,
by doing thousands of suspend/resume cycles with 4 processes doing FPU
operations running. Without the patch, a process is killed after a
few hundreds cycles by a SIGFPE.

Cc: Duncan Laurie <dlaurie@chromium.org>
Cc: Olof Johansson <olofj@chromium.org>
Cc: <stable@kernel.org> v3.4+ # for 3.4 need to replace this_cpu_write by percpu_write
Signed-off-by: Vincent Palatin <vpalatin@chromium.org>
Link: http://lkml.kernel.org/r/1354306532-1014-1-git-send-email-vpalatin@chromium.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 831dbb9..41ab26e 100644 (file)
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -399,14 +399,17 @@ static inline void drop_init_fpu(struct task_struct *tsk)
 typedef struct { int preload; } fpu_switch_t;
 
 /*
- * FIXME! We could do a totally lazy restore, but we need to
- * add a per-cpu "this was the task that last touched the FPU
- * on this CPU" variable, and the task needs to have a "I last
- * touched the FPU on this CPU" and check them.
+ * Must be run with preemption disabled: this clears the fpu_owner_task,
+ * on this CPU.
  *
- * We don't do that yet, so "fpu_lazy_restore()" always returns
- * false, but some day..
+ * This will disable any lazy FPU state restore of the current FPU state,
+ * but if the current thread owns the FPU, it will still be saved by.
  */
+static inline void __cpu_disable_lazy_restore(unsigned int cpu)
+{
+       per_cpu(fpu_owner_task, cpu) = NULL;
+}
+
 static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
 {
        return new == this_cpu_read_stable(fpu_owner_task) &&

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c80a33b..f3e2ec8 100644 (file)
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -68,6 +68,8 @@
 #include <asm/mwait.h>
 #include <asm/apic.h>
 #include <asm/io_apic.h>
+#include <asm/i387.h>
+#include <asm/fpu-internal.h>
 #include <asm/setup.h>
 #include <asm/uv/uv.h>
 #include <linux/mc146818rtc.h>
@@ -818,6 +820,9 @@ int __cpuinit native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 
        per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
 
+       /* the FPU context is blank, nobody can own it */
+       __cpu_disable_lazy_restore(cpu);
+
        err = do_boot_cpu(apicid, cpu, tidle);
        if (err) {
                pr_debug("do_boot_cpu failed %d\n", err);